File size: 274 Bytes
52a881a 6bfad80 52a881a 6bfad80 | 1 2 3 4 5 6 7 8 9 10 11 | # Inference
Two runtime tracks are provided:
- `full_precision/`: single-image inference, multi-turn chat, and FastAPI service
- `int4_quantized/`: single-image inference, multi-turn chat, and FastAPI service for the INT4 path
Model weights directory:
- `./checkpoints`
|